Style-Agnostic Reinforcement Learning
Not on the map. Why?
Abstract (arXiv)
We present a novel method of learning style-agnostic representation using both style transfer and adversarial learning in the reinforcement learning framework. The style, here, refers to task-irrelevant details such as the color of the background in the images, where generalizing the learned policy across environments with different styles is still a challenge. Focusing on learning style-agnostic representations, our method trains the actor with diverse image styles generated from an inherent adversarial style perturbation generator, which plays a min-max game between the actor and the generator, without demanding expert knowledge for data augmentation or additional class labels for adversarial training. We verify that our method achieves competitive or better performances than the state-of-the-art approaches on Procgen and Distracting Control Suite benchmarks, and further investigate the features extracted from our model, showing that the model better captures the invariants and is less distracted by the shifted style. The code is available at https://github.com/POSTECH-CVLab/style-agnostic-RL.
Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 40 of its 49 references that are in the map. First posted on arXiv 31 Aug 2022.
Builds on
40 of 49 references.
References · 40
- 2017Proximal Policy Optimization Algorithmscited by 15,215
- 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,733
- 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 6,013
- 2018Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actorcited by 4,885
- 2013Playing Atari with Deep Reinforcement Learningcited by 3,274
- 2017Arbitrary Style Transfer in Real-time with Adaptive Instance Normalizationcited by 2,010
- 2019Dream to Control: Learning Behaviors by Latent Imaginationcited by 1,653
- 2018World Modelscited by 1,513
- 2017Domain Randomization for Transferring Deep Neural Networks from Simulation to the Real Worldcited by 1,498
- 2016Instance Normalization: The Missing Ingredient for Fast Stylizationcited by 1,198
- 2018DeepMind Control Suitecited by 956
- 2018IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architecturescited by 883
28 more
- 2015End-to-End Training of Deep Visuomotor Policiescited by 875
- 2020CURL: Contrastive Unsupervised Representations for Reinforcement Learningcited by 760
- 2020Image Augmentation Is All You Need: Regularizing Deep Reinforcement Learning from Pixelscited by 585
- 2021Domain Generalization with MixStylecited by 566
- 2019Leveraging Procedural Generation to Benchmark Reinforcement Learningcited by 483
- 2020Reinforcement Learning with Augmented Datacited by 468
- 2017Robust Adversarial Reinforcement Learningcited by 451
- 2016Target-driven Visual Navigation in Indoor Scenes using Deep Reinforcement Learningcited by 366
- 2018Quantifying Generalization in Reinforcement Learningcited by 352
- 2016A Learned Representation For Artistic Stylecited by 341
- 2019Improving Sample Efficiency in Model-Free Reinforcement Learning from Imagescited by 274
- 2019Stochastic Latent Actor-Critic: Deep Reinforcement Learning with a Latent Variable Modelcited by 231
- 2017Improved Texture Networks: Maximizing Quality and Diversity in Feed-forward Stylization and Texture Synthesiscited by 215
- 2018A Study on Overfitting in Deep Reinforcement Learningcited by 174
- 2017DARLA: Improving Zero-Shot Transfer in Reinforcement Learningcited by 149
- 2017Using Simulation and Domain Adaptation to Improve Efficiency of Deep Robotic Graspingcited by 144
- 2020Generalization in Reinforcement Learning by Soft Data Augmentationcited by 137
- 2018Constructing Unrestricted Adversarial Examples with Generative Modelscited by 135
- 2020Self-Supervised Policy Adaptation during Deploymentcited by 123
- 2021Stabilizing Deep Q-Learning with ConvNets and Vision Transformers under Data Augmentationcited by 105
- 2019Network Randomization: A Simple Technique for Generalization in Deep Reinforcement Learningcited by 104
- 2021The Distracting Control Suite -- A Challenging Benchmark for Reinforcement Learning from Pixelscited by 100
- 2019Functional Adversarial Attackscited by 82
- 2020Automatic Data Augmentation for Generalization in Deep Reinforcement Learningcited by 71
- 2021Feature-based Style Randomization for Domain Generalizationcited by 34
- 2021Cross-Trajectory Representation Learning for Zero-Shot Generalization in RLcited by 20
- 2021Domain Adversarial Reinforcement Learningcited by 19
- 2020Towards Feature Space Adversarial Attackcited by 11
Built on by
Citing papers per year: 2023: 1; 2024: 1.
2 papers.